Files
math-1b-sft-numinamath-bs51…/trainer_log.jsonl

85 lines
16 KiB
Plaintext
Raw Permalink Normal View History

{"current_steps": 20, "total_steps": 1679, "loss": 1.9374, "lr": 3.7254901960784316e-06, "epoch": 0.011911852293031567, "percentage": 1.19, "elapsed_time": "0:01:11", "remaining_time": "1:38:22"}
{"current_steps": 40, "total_steps": 1679, "loss": 1.5063, "lr": 7.647058823529411e-06, "epoch": 0.023823704586063133, "percentage": 2.38, "elapsed_time": "0:02:12", "remaining_time": "1:30:16"}
{"current_steps": 60, "total_steps": 1679, "loss": 0.9789, "lr": 9.999404197526844e-06, "epoch": 0.0357355568790947, "percentage": 3.57, "elapsed_time": "0:03:12", "remaining_time": "1:26:41"}
{"current_steps": 80, "total_steps": 1679, "loss": 0.7814, "lr": 9.99270305028903e-06, "epoch": 0.047647409172126266, "percentage": 4.76, "elapsed_time": "0:04:15", "remaining_time": "1:25:09"}
{"current_steps": 100, "total_steps": 1679, "loss": 0.7043, "lr": 9.978566016361393e-06, "epoch": 0.05955926146515783, "percentage": 5.96, "elapsed_time": "0:05:24", "remaining_time": "1:25:22"}
{"current_steps": 120, "total_steps": 1679, "loss": 0.667, "lr": 9.95701415074788e-06, "epoch": 0.0714711137581894, "percentage": 7.15, "elapsed_time": "0:06:26", "remaining_time": "1:23:40"}
{"current_steps": 140, "total_steps": 1679, "loss": 0.6471, "lr": 9.928079551738542e-06, "epoch": 0.08338296605122096, "percentage": 8.34, "elapsed_time": "0:07:28", "remaining_time": "1:22:09"}
{"current_steps": 160, "total_steps": 1679, "loss": 0.6362, "lr": 9.891805313103928e-06, "epoch": 0.09529481834425253, "percentage": 9.53, "elapsed_time": "0:08:26", "remaining_time": "1:20:08"}
{"current_steps": 180, "total_steps": 1679, "loss": 0.6173, "lr": 9.848245459913323e-06, "epoch": 0.1072066706372841, "percentage": 10.72, "elapsed_time": "0:09:26", "remaining_time": "1:18:39"}
{"current_steps": 200, "total_steps": 1679, "loss": 0.6172, "lr": 9.797464868072489e-06, "epoch": 0.11911852293031566, "percentage": 11.91, "elapsed_time": "0:10:26", "remaining_time": "1:17:11"}
{"current_steps": 220, "total_steps": 1679, "loss": 0.6081, "lr": 9.739539167700649e-06, "epoch": 0.13103037522334723, "percentage": 13.1, "elapsed_time": "0:11:28", "remaining_time": "1:16:06"}
{"current_steps": 240, "total_steps": 1679, "loss": 0.5972, "lr": 9.674554630490727e-06, "epoch": 0.1429422275163788, "percentage": 14.29, "elapsed_time": "0:12:33", "remaining_time": "1:15:19"}
{"current_steps": 260, "total_steps": 1679, "loss": 0.5892, "lr": 9.60260804122051e-06, "epoch": 0.15485407980941035, "percentage": 15.49, "elapsed_time": "0:13:31", "remaining_time": "1:13:46"}
{"current_steps": 280, "total_steps": 1679, "loss": 0.5889, "lr": 9.523806553606157e-06, "epoch": 0.16676593210244192, "percentage": 16.68, "elapsed_time": "0:14:35", "remaining_time": "1:12:54"}
{"current_steps": 300, "total_steps": 1679, "loss": 0.5879, "lr": 9.438267530712727e-06, "epoch": 0.1786777843954735, "percentage": 17.87, "elapsed_time": "0:15:35", "remaining_time": "1:11:41"}
{"current_steps": 320, "total_steps": 1679, "loss": 0.5824, "lr": 9.34611837015938e-06, "epoch": 0.19058963668850507, "percentage": 19.06, "elapsed_time": "0:16:34", "remaining_time": "1:10:23"}
{"current_steps": 340, "total_steps": 1679, "loss": 0.5799, "lr": 9.247496314379634e-06, "epoch": 0.20250148898153664, "percentage": 20.25, "elapsed_time": "0:17:33", "remaining_time": "1:09:07"}
{"current_steps": 360, "total_steps": 1679, "loss": 0.5694, "lr": 9.142548246219212e-06, "epoch": 0.2144133412745682, "percentage": 21.44, "elapsed_time": "0:18:31", "remaining_time": "1:07:53"}
{"current_steps": 380, "total_steps": 1679, "loss": 0.5702, "lr": 9.031430470175958e-06, "epoch": 0.22632519356759975, "percentage": 22.63, "elapsed_time": "0:19:32", "remaining_time": "1:06:47"}
{"current_steps": 400, "total_steps": 1679, "loss": 0.5622, "lr": 8.914308479607592e-06, "epoch": 0.23823704586063132, "percentage": 23.82, "elapsed_time": "0:20:31", "remaining_time": "1:05:36"}
{"current_steps": 420, "total_steps": 1679, "loss": 0.561, "lr": 8.791356710254026e-06, "epoch": 0.25014889815366287, "percentage": 25.01, "elapsed_time": "0:21:30", "remaining_time": "1:04:28"}
{"current_steps": 440, "total_steps": 1679, "loss": 0.5626, "lr": 8.662758280441353e-06, "epoch": 0.26206075044669447, "percentage": 26.21, "elapsed_time": "0:22:26", "remaining_time": "1:03:12"}
{"current_steps": 460, "total_steps": 1679, "loss": 0.5624, "lr": 8.528704718354392e-06, "epoch": 0.273972602739726, "percentage": 27.4, "elapsed_time": "0:23:25", "remaining_time": "1:02:03"}
{"current_steps": 480, "total_steps": 1679, "loss": 0.5592, "lr": 8.389395676784025e-06, "epoch": 0.2858844550327576, "percentage": 28.59, "elapsed_time": "0:24:28", "remaining_time": "1:01:08"}
{"current_steps": 500, "total_steps": 1679, "loss": 0.5564, "lr": 8.245038635774144e-06, "epoch": 0.29779630732578916, "percentage": 29.78, "elapsed_time": "0:25:26", "remaining_time": "0:59:58"}
{"current_steps": 520, "total_steps": 1679, "loss": 0.5525, "lr": 8.095848593611045e-06, "epoch": 0.3097081596188207, "percentage": 30.97, "elapsed_time": "0:26:24", "remaining_time": "0:58:51"}
{"current_steps": 540, "total_steps": 1679, "loss": 0.553, "lr": 7.942047746615561e-06, "epoch": 0.3216200119118523, "percentage": 32.16, "elapsed_time": "0:27:22", "remaining_time": "0:57:44"}
{"current_steps": 560, "total_steps": 1679, "loss": 0.5507, "lr": 7.783865158214768e-06, "epoch": 0.33353186420488384, "percentage": 33.35, "elapsed_time": "0:28:26", "remaining_time": "0:56:49"}
{"current_steps": 580, "total_steps": 1679, "loss": 0.5459, "lr": 7.621536417786159e-06, "epoch": 0.34544371649791544, "percentage": 34.54, "elapsed_time": "0:29:24", "remaining_time": "0:55:42"}
{"current_steps": 600, "total_steps": 1679, "loss": 0.5535, "lr": 7.455303289782414e-06, "epoch": 0.357355568790947, "percentage": 35.74, "elapsed_time": "0:30:19", "remaining_time": "0:54:32"}
{"current_steps": 620, "total_steps": 1679, "loss": 0.5502, "lr": 7.285413353659285e-06, "epoch": 0.36926742108397853, "percentage": 36.93, "elapsed_time": "0:31:16", "remaining_time": "0:53:25"}
{"current_steps": 640, "total_steps": 1679, "loss": 0.5502, "lr": 7.1121196351429235e-06, "epoch": 0.38117927337701013, "percentage": 38.12, "elapsed_time": "0:32:14", "remaining_time": "0:52:20"}
{"current_steps": 660, "total_steps": 1679, "loss": 0.5442, "lr": 6.935680229385788e-06, "epoch": 0.3930911256700417, "percentage": 39.31, "elapsed_time": "0:33:08", "remaining_time": "0:51:10"}
{"current_steps": 680, "total_steps": 1679, "loss": 0.549, "lr": 6.7563579165724e-06, "epoch": 0.4050029779630733, "percentage": 40.5, "elapsed_time": "0:34:07", "remaining_time": "0:50:08"}
{"current_steps": 700, "total_steps": 1679, "loss": 0.5413, "lr": 6.574419770547455e-06, "epoch": 0.4169148302561048, "percentage": 41.69, "elapsed_time": "0:35:05", "remaining_time": "0:49:04"}
{"current_steps": 720, "total_steps": 1679, "loss": 0.5398, "lr": 6.390136761049138e-06, "epoch": 0.4288266825491364, "percentage": 42.88, "elapsed_time": "0:36:02", "remaining_time": "0:48:00"}
{"current_steps": 740, "total_steps": 1679, "loss": 0.544, "lr": 6.2037833501401236e-06, "epoch": 0.44073853484216796, "percentage": 44.07, "elapsed_time": "0:36:58", "remaining_time": "0:46:55"}
{"current_steps": 760, "total_steps": 1679, "loss": 0.5412, "lr": 6.015637083437249e-06, "epoch": 0.4526503871351995, "percentage": 45.27, "elapsed_time": "0:37:56", "remaining_time": "0:45:52"}
{"current_steps": 780, "total_steps": 1679, "loss": 0.5424, "lr": 5.825978176748709e-06, "epoch": 0.4645622394282311, "percentage": 46.46, "elapsed_time": "0:38:54", "remaining_time": "0:44:51"}
{"current_steps": 800, "total_steps": 1679, "loss": 0.5405, "lr": 5.635089098734394e-06, "epoch": 0.47647409172126265, "percentage": 47.65, "elapsed_time": "0:40:00", "remaining_time": "0:43:57"}
{"current_steps": 820, "total_steps": 1679, "loss": 0.5453, "lr": 5.443254150210946e-06, "epoch": 0.48838594401429425, "percentage": 48.84, "elapsed_time": "0:41:00", "remaining_time": "0:42:57"}
{"current_steps": 840, "total_steps": 1679, "loss": 0.5381, "lr": 5.250759040728082e-06, "epoch": 0.5002977963073257, "percentage": 50.03, "elapsed_time": "0:41:56", "remaining_time": "0:41:53"}
{"current_steps": 860, "total_steps": 1679, "loss": 0.5404, "lr": 5.057890463046825e-06, "epoch": 0.5122096486003573, "percentage": 51.22, "elapsed_time": "0:42:53", "remaining_time": "0:40:50"}
{"current_steps": 880, "total_steps": 1679, "loss": 0.5403, "lr": 4.864935666153388e-06, "epoch": 0.5241215008933889, "percentage": 52.41, "elapsed_time": "0:43:51", "remaining_time": "0:39:49"}
{"current_steps": 900, "total_steps": 1679, "loss": 0.5332, "lr": 4.672182027444649e-06, "epoch": 0.5360333531864205, "percentage": 53.6, "elapsed_time": "0:44:50", "remaining_time": "0:38:48"}
{"current_steps": 920, "total_steps": 1679, "loss": 0.5344, "lr": 4.4799166247223576e-06, "epoch": 0.547945205479452, "percentage": 54.79, "elapsed_time": "0:45:50", "remaining_time": "0:37:49"}
{"current_steps": 940, "total_steps": 1679, "loss": 0.534, "lr": 4.2884258086335755e-06, "epoch": 0.5598570577724836, "percentage": 55.99, "elapsed_time": "0:46:48", "remaining_time": "0:36:47"}
{"current_steps": 960, "total_steps": 1679, "loss": 0.5358, "lr": 4.09799477619407e-06, "epoch": 0.5717689100655152, "percentage": 57.18, "elapsed_time": "0:47:49", "remaining_time": "0:35:49"}
{"current_steps": 980, "total_steps": 1679, "loss": 0.53, "lr": 3.908907146029905e-06, "epoch": 0.5836807623585467, "percentage": 58.37, "elapsed_time": "0:48:47", "remaining_time": "0:34:47"}
{"current_steps": 1000, "total_steps": 1679, "loss": 0.5377, "lr": 3.721444535969774e-06, "epoch": 0.5955926146515783, "percentage": 59.56, "elapsed_time": "0:49:44", "remaining_time": "0:33:46"}
{"current_steps": 1020, "total_steps": 1679, "loss": 0.5331, "lr": 3.5358861436172487e-06, "epoch": 0.6075044669446099, "percentage": 60.75, "elapsed_time": "0:50:38", "remaining_time": "0:32:43"}
{"current_steps": 1040, "total_steps": 1679, "loss": 0.5279, "lr": 3.352508330527581e-06, "epoch": 0.6194163192376414, "percentage": 61.94, "elapsed_time": "0:51:36", "remaining_time": "0:31:42"}
{"current_steps": 1060, "total_steps": 1679, "loss": 0.5332, "lr": 3.1715842106083704e-06, "epoch": 0.631328171530673, "percentage": 63.13, "elapsed_time": "0:52:34", "remaining_time": "0:30:42"}
{"current_steps": 1080, "total_steps": 1679, "loss": 0.5322, "lr": 2.993383243357134e-06, "epoch": 0.6432400238237046, "percentage": 64.32, "elapsed_time": "0:53:32", "remaining_time": "0:29:41"}
{"current_steps": 1100, "total_steps": 1679, "loss": 0.531, "lr": 2.8181708325415603e-06, "epoch": 0.6551518761167362, "percentage": 65.52, "elapsed_time": "0:54:31", "remaining_time": "0:28:42"}
{"current_steps": 1120, "total_steps": 1679, "loss": 0.533, "lr": 2.646207930920175e-06, "epoch": 0.6670637284097677, "percentage": 66.71, "elapsed_time": "0:55:30", "remaining_time": "0:27:42"}
{"current_steps": 1140, "total_steps": 1679, "loss": 0.5346, "lr": 2.4777506515921222e-06, "epoch": 0.6789755807027993, "percentage": 67.9, "elapsed_time": "0:56:26", "remaining_time": "0:26:41"}
{"current_steps": 1160, "total_steps": 1679, "loss": 0.5288, "lr": 2.31304988655489e-06, "epoch": 0.6908874329958309, "percentage": 69.09, "elapsed_time": "0:57:22", "remaining_time": "0:25:40"}
{"current_steps": 1180, "total_steps": 1679, "loss": 0.5246, "lr": 2.152350933038097e-06, "epoch": 0.7027992852888624, "percentage": 70.28, "elapsed_time": "0:58:22", "remaining_time": "0:24:40"}
{"current_steps": 1200, "total_steps": 1679, "loss": 0.5284, "lr": 1.995893128169846e-06, "epoch": 0.714711137581894, "percentage": 71.47, "elapsed_time": "0:59:20", "remaining_time": "0:23:41"}
{"current_steps": 1220, "total_steps": 1679, "loss": 0.5258, "lr": 1.8439094925197593e-06, "epoch": 0.7266229898749256, "percentage": 72.66, "elapsed_time": "1:00:16", "remaining_time": "0:22:40"}
{"current_steps": 1240, "total_steps": 1679, "loss": 0.5317, "lr": 1.6966263830495939e-06, "epoch": 0.7385348421679571, "percentage": 73.85, "elapsed_time": "1:01:15", "remaining_time": "0:21:41"}
{"current_steps": 1260, "total_steps": 1679, "loss": 0.5334, "lr": 1.554263155988287e-06, "epoch": 0.7504466944609887, "percentage": 75.04, "elapsed_time": "1:02:12", "remaining_time": "0:20:41"}
{"current_steps": 1280, "total_steps": 1679, "loss": 0.5252, "lr": 1.4170318401335858e-06, "epoch": 0.7623585467540203, "percentage": 76.24, "elapsed_time": "1:03:12", "remaining_time": "0:19:42"}
{"current_steps": 1300, "total_steps": 1679, "loss": 0.5286, "lr": 1.2851368210667426e-06, "epoch": 0.7742703990470519, "percentage": 77.43, "elapsed_time": "1:04:11", "remaining_time": "0:18:42"}
{"current_steps": 1320, "total_steps": 1679, "loss": 0.5278, "lr": 1.158774536750698e-06, "epoch": 0.7861822513400833, "percentage": 78.62, "elapsed_time": "1:05:09", "remaining_time": "0:17:43"}
{"current_steps": 1340, "total_steps": 1679, "loss": 0.5256, "lr": 1.038133184965001e-06, "epoch": 0.798094103633115, "percentage": 79.81, "elapsed_time": "1:06:08", "remaining_time": "0:16:43"}
{"current_steps": 1360, "total_steps": 1679, "loss": 0.5352, "lr": 9.233924430133024e-07, "epoch": 0.8100059559261465, "percentage": 81.0, "elapsed_time": "1:07:07", "remaining_time": "0:15:44"}
{"current_steps": 1380, "total_steps": 1679, "loss": 0.5335, "lr": 8.147232001207894e-07, "epoch": 0.821917808219178, "percentage": 82.19, "elapsed_time": "1:08:05", "remaining_time": "0:14:45"}
{"current_steps": 1400, "total_steps": 1679, "loss": 0.527, "lr": 7.122873029201732e-07, "epoch": 0.8338296605122096, "percentage": 83.38, "elapsed_time": "1:09:05", "remaining_time": "0:13:46"}
{"current_steps": 1420, "total_steps": 1679, "loss": 0.5329, "lr": 6.162373144052636e-07, "epoch": 0.8457415128052412, "percentage": 84.57, "elapsed_time": "1:10:03", "remaining_time": "0:12:46"}
{"current_steps": 1440, "total_steps": 1679, "loss": 0.5311, "lr": 5.267162867111387e-07, "epoch": 0.8576533650982728, "percentage": 85.77, "elapsed_time": "1:11:02", "remaining_time": "0:11:47"}
{"current_steps": 1460, "total_steps": 1679, "loss": 0.5249, "lr": 4.43857548059321e-07, "epoch": 0.8695652173913043, "percentage": 86.96, "elapsed_time": "1:12:04", "remaining_time": "0:10:48"}
{"current_steps": 1480, "total_steps": 1679, "loss": 0.5349, "lr": 3.6778450418527735e-07, "epoch": 0.8814770696843359, "percentage": 88.15, "elapsed_time": "1:13:00", "remaining_time": "0:09:49"}
{"current_steps": 1500, "total_steps": 1679, "loss": 0.531, "lr": 2.9861045454396943e-07, "epoch": 0.8933889219773675, "percentage": 89.34, "elapsed_time": "1:13:55", "remaining_time": "0:08:49"}
{"current_steps": 1520, "total_steps": 1679, "loss": 0.5377, "lr": 2.3643842356722124e-07, "epoch": 0.905300774270399, "percentage": 90.53, "elapsed_time": "1:14:52", "remaining_time": "0:07:49"}
{"current_steps": 1540, "total_steps": 1679, "loss": 0.523, "lr": 1.8136100722418003e-07, "epoch": 0.9172126265634306, "percentage": 91.72, "elapsed_time": "1:15:48", "remaining_time": "0:06:50"}
{"current_steps": 1560, "total_steps": 1679, "loss": 0.5285, "lr": 1.3346023511343842e-07, "epoch": 0.9291244788564622, "percentage": 92.91, "elapsed_time": "1:16:45", "remaining_time": "0:05:51"}
{"current_steps": 1580, "total_steps": 1679, "loss": 0.5363, "lr": 9.280744829216982e-08, "epoch": 0.9410363311494937, "percentage": 94.1, "elapsed_time": "1:17:42", "remaining_time": "0:04:52"}
{"current_steps": 1600, "total_steps": 1679, "loss": 0.5273, "lr": 5.9463193024269505e-08, "epoch": 0.9529481834425253, "percentage": 95.29, "elapsed_time": "1:18:42", "remaining_time": "0:03:53"}
{"current_steps": 1620, "total_steps": 1679, "loss": 0.5307, "lr": 3.347713060571855e-08, "epoch": 0.9648600357355569, "percentage": 96.49, "elapsed_time": "1:19:39", "remaining_time": "0:02:54"}
{"current_steps": 1640, "total_steps": 1679, "loss": 0.529, "lr": 1.4887963401492011e-08, "epoch": 0.9767718880285885, "percentage": 97.68, "elapsed_time": "1:20:36", "remaining_time": "0:01:55"}
{"current_steps": 1660, "total_steps": 1679, "loss": 0.5298, "lr": 3.7233772041533888e-09, "epoch": 0.98868374032162, "percentage": 98.87, "elapsed_time": "1:21:33", "remaining_time": "0:00:56"}
{"current_steps": 1679, "total_steps": 1679, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:22:38", "remaining_time": "0:00:00"}